© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13146
    Prev
    Next
    INDEX
    Explanations

    client channel setting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĢĮå¾ĹåIJį
    -0.08
    åļı
    -0.07
     cor
    -0.06
    æĪIJç«ĭçļĦ
    -0.06
    kers
    -0.06
    кÑĬ
    -0.06
    æĿ¥å®ŀçİ°
    -0.06
     _,
    -0.06
    iry
    -0.06
     Nett
    -0.06
    POSITIVE LOGITS
     (!((
    0.09
    æľĢæĸ°èµĦ讯
    0.08
    uhr
    0.08
    ï¼Ŀï¼Ŀ
    0.08
    ourke
    0.08
    upos
    0.08
    #=
    0.07
    è¶ħè¿ĩ约
    0.07
    alas
    0.07
    èħĨ
    0.07
    Activations Density 0.002%

    No Known Activations